Elo-Evolve: A Co-evolutionary Framework for Language Model Alignment

• URL: http://arxiv.org/abs/2602.13575v1
• Date: Sat, 14 Feb 2026 03:18:52 GMT
• Title: Elo-Evolve: A Co-evolutionary Framework for Language Model Alignment
• Abstract summary: Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions.<n>We introduce Elo-Evolve, a co-evolutionary framework that redefines alignment as dynamic multi-agent competition within an adaptive opponent pool.
• Score: 9.926056056629239
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcity, noise sensitivity, and training instability. We introduce Elo-Evolve, a co-evolutionary framework that redefines alignment as dynamic multi-agent competition within an adaptive opponent pool. Our approach makes two key innovations: (1) eliminating Bradley-Terry model dependencies by learning directly from binary win/loss outcomes in pairwise competitions, and (2) implementing Elo-orchestrated opponent selection that provides automatic curriculum learning through temperature-controlled sampling. We ground our approach in PAC learning theory, demonstrating that pairwise comparison achieves superior sample complexity and empirically validate a 4.5x noise reduction compared to absolute scoring approaches. Experimentally, we train a Qwen2.5-7B model using our framework with opponents including Qwen2.5-14B, Qwen2.5-32B, and Qwen3-8B models. Results demonstrate a clear performance hierarchy: point-based methods < static pairwise training < Elo-Evolve across Alpaca Eval 2.0 and MT-Bench, validating the progressive benefits of pairwise comparison and dynamic opponent selection for LLM alignment.

Related papers

• Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs [24.816746511570244]
  Team-based self-Play with dual Adaptive Weighting (TPAW) is a novel self-play algorithm designed to improve alignment in a fully self-supervised setting.<n>TPAW iteratively refines alignment without requiring additional human supervision.
  arXiv  Detail & Related papers  (2026-05-11T03:17:31Z)
• When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning [30.162034423611292]
  We propose an unsupervised self-evolution training framework for multimodal reasoning.<n>It achieves stable performance improvements without using human-annotated answers or external reward models.<n>Our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-22T15:22:19Z)
• LLM Routing with Dueling Feedback [49.67815163970033]
  We study the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost.<n>We formulate routing as contextual dueling bandits, learning from pairwise preference feedback rather than absolute scores.<n>We introduce Category-Calibrated Fine-Tuning (CCFT), a representation-learning method that derives model embeddings from offline data using contrastive fine-tuning with categorical weighting.
  arXiv  Detail & Related papers  (2025-10-01T12:52:25Z)
• DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation [0.4660328753262075]
  DualReward is a novel reinforcement learning framework for automatic distractor generation in cloze tests.<n>We evaluate our approach on both passage-level (CLOTH-F) and sentence-level (MCQ) cloze test datasets.
  arXiv  Detail & Related papers  (2025-07-16T03:39:36Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• Joint Training for Selective Prediction [5.662924503089369]
  Selective Prediction methods determine when to adopt a classifier's output versus defer to a human. One previous method involves learning a deferral model based on engineered features. We introduce a novel joint-training approach that simultaneously optimize learned representations used by the classifier module and a learned deferral policy.
  arXiv  Detail & Related papers  (2024-10-31T15:28:26Z)
• Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models [0.0]
  This work proposes a 3 Phase technique to adjust a base model for a classification task. We adapt the model's signal to the data distribution by performing further training with a Denoising Autoencoder (DAE) In addition, we introduce a new data augmentation approach for Supervised Contrastive Learning to correct the unbalanced datasets.
  arXiv  Detail & Related papers  (2024-05-23T11:08:35Z)
• Robust Learning with Progressive Data Expansion Against Spurious Correlation [65.83104529677234]
  We study the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features. Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process. We propose a new training algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance.
  arXiv  Detail & Related papers  (2023-06-08T05:44:06Z)
• Pre-training Language Model as a Multi-perspective Course Learner [103.17674402415582]
  This study proposes a multi-perspective course learning (MCL) method for sample-efficient pre-training. In this study, three self-supervision courses are designed to alleviate inherent flaws of "tug-of-war" dynamics. Our method significantly improves ELECTRA's average performance by 2.8% and 3.2% absolute points respectively on GLUE and SQuAD 2.0 benchmarks.
  arXiv  Detail & Related papers  (2023-05-06T09:02:10Z)
• Unifying Language Learning Paradigms [96.35981503087567]
  We present a unified framework for pre-training models that are universally effective across datasets and setups. We show how different pre-training objectives can be cast as one another and how interpolating between different objectives can be effective. Our model also achieve strong results at in-context learning, outperforming 175B GPT-3 on zero-shot SuperGLUE and tripling the performance of T5-XXL on one-shot summarization.
  arXiv  Detail & Related papers  (2022-05-10T19:32:20Z)
• Adaptive Consistency Regularization for Semi-Supervised Transfer Learning [31.66745229673066]
  We consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization. Our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and MixMatch.
  arXiv  Detail & Related papers  (2021-03-03T05:46:39Z)
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility [54.179859639868646]
  Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data. There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups. We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
  arXiv  Detail & Related papers  (2020-06-15T10:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.